---
name: remove-ai-tells
description: Strip the structural and lexical patterns that mark text as AI-written,
while preserving the author's meaning and any stylistic choices that are genuinely
theirs. Targets the real tells — hedge stacking ("it's worth noting that," "it's
important to remember"), the "not just X, it's Y" construction, tricolon abuse (three
parallel phrases for everything), restating-the-intro conclusions, vague intensifiers
("truly," "deeply," "profoundly"), and overused vocabulary ("delve," "tapestry,"
"navigate t
compatibility: None required. Pure local text editing.
allowed-tools: Read Edit Write
---
remove-ai-tells
Strip the structural and lexical patterns that mark text as AI-written, while preserving the author's meaning and any stylistic choices that are genuinely theirs. Targets the real tells — hedge stacking ("it's worth noting that," "it's important to remember"), the "not just X, it's Y" construction, tricolon abuse (thr…
- Instant access
- Portable SKILL.md
- Free updates
One file · Writes files
The body stays locked until purchase — here is precisely what unlocks.
Writes files
Declares Read, Edit, Write.
- Writes files Edit, Write
- Reads files Read
What you install
A skill directory you can read the head of before you trust it.
- The SKILL.md file itself1 file · 11.2 KB
- Writes filesRead, Edit, Write
- Stated runtimesNone required. Pure local text editing.
- Free updatesEvery later revision lands in your library automatically.
- SKILL.md 11.2 KB · 2.8K tk
What it costs to keep loaded
A skill loads in stages — the index entry is always resident, the body only when the skill fires.
Counted with a general-purpose tokenizer, so a particular runtime will differ by a few percent. The skill makes no model call of its own, so there are no output tokens to pay for beyond the reply you were already getting.
Specifics and common questions
- Version
- v1
- Licence
- Not stated
- Allowed tools
- Read, Edit, Write
- Ships as
- 1 file · 11.2 KB
- Runs in
- None required. Pure local text editing.
- Spec
- agentskills.io v1
- Context cost
- 2,825 tokens116 always resident · the rest only when the skill fires.
- Published
- Apr 28, 2026
- Updated
- Aug 1, 2026
- Reviews
- No reviews yet
Experimental bio with extra words. Experimental bio with extra words.
-
What does remove-ai-tells do?
Strip the structural and lexical patterns that mark text as AI-written, while preserving the author's meaning and any stylistic choices that are genuinely theirs. Targets the real tells — hedge stacking ("it's worth noting that," "it's important to remember"), the "not just X, it's Y" construction, tricolon abuse (three parallel phrases for everything), restating-the-intro conclusions, vague inte…
-
Who is remove-ai-tells best for?
remove-ai-tells is built for operations-process use cases. and is particularly useful for tells, remove, and abuse.
-
How much does remove-ai-tells cost?
remove-ai-tells is free to claim on Sigrix.
-
How do I use remove-ai-tells?
remove-ai-tells is delivered as a portable SKILL.md module you own on Sigrix. Drop it into Claude Code, claude.ai, or the Claude API and tailor the instructions to your own workflow.
More skills
clean-pasted-text
Fix text that was pasted from a PDF, Word doc, webpage, email, or chat and arrived broken. Repairs smart quotes and curly apostrophes, removes non-breaking spaces and zero-width characters, fixes mid-word line breaks and hyphenation from PDF column wraps, normalizes bullets and dashes, collapses double spaces after periods, strips invisible Unicode trash, and rebuilds paragraph structure when newlines were lost or doubled. Use when the user says the text "looks weird," "won't format right," "has
faq-schema-extractor
Turns finished drafts into structured Q&A — a visible FAQ section plus valid FAQPage JSON-LD — for content and SEO teams who want clear, parseable answers without bolting fake questions onto every page.
convert-to-markdown
Converts HTML, rich text, or pasted Word/Docs/Notion content into clean GitHub-Flavored Markdown. Preserves structure, strips presentational junk, tracking, and ad widgets. (197 chars)
trend-safety-gate
Paste a rising-trends list, get a publishability verdict per term. Harm events, live recalls and third-party IP blocked, ambiguous names flagged, clean terms cleared. For content and SEO teams.